Learning Short-Cut Connections for Object Counting

05/08/2018
by   Daniel Oñoro-Rubio, et al.
0

Object counting is an important task in computer vision due to its growing demand in applications such as traffic monitoring or surveillance. In this paper, we consider object counting as a learning problem of a joint feature extraction and pixel-wise object density estimation with Convolutional-Deconvolutional networks. We propose a novel counting model, named Gated U-Net (GU-Net). Specifically, we propose to enrich the U-Net architecture with the concept of learnable short-cut connections. Standard short-cut connections are connections between layers in deep neural networks which skip at least one intermediate layer. Instead of simply setting short-cut connections, we propose to learn these connections from data. Therefore, our short-cut can work as a gating unit, which optimizes the flow of information between convolutional and deconvolutional layers in the U-Net architecture. We evaluate the proposed GU-Net architecture on three commonly used benchmark data sets for object counting. GU-Nets consistently outperform the base U-Net architecture, and achieve state-of-the-art performance.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset